Designing application-specific neural networks using the structured genetic algorithm

Dasgupta, Dipankar; McGregor, D. R.

doi:10.1109/cogann.1992.273946

Cited by 95 publications

(52 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A structured genetic algorithm was proposed in [263], which simultaneously optimized both architectures and weights. It was found that the simultaneous optimization of both weight and architecture lead to a better generalization [56,197,264,265].…”

Section: Combination Of Fnn Components Optimizationmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

457

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract

Section: Combination Of Fnn Components Optimizationmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

457

154

View full text Add to dashboard Cite

show abstract

“…Perhaps the simplest of these is the Structured Genetic Algorithm (sGA) (Dasgupta and McGregor 1992), in which one bit string represents each network's connection matrix and another bit string represents the weights of each link. These bit strings are then evolved using standard genetic algorithms.…”

Section: Evolutionary Computationmentioning

confidence: 99%

Adaptive Representations for Reinforcement Learning

Stone

Whiteson

2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

AcknowledgmentsFirst and foremost, I would like to thank my parents, without whose tireless support and encouragement none of my achievements, academic or otherwise, would have been possible.In particular, I am grateful to my father, Adam, for instilling in me a deep enmity for ignorance, a lasting appreciation for the beauty of mathematics, and an uncompromising respect for the rigor of science. I am grateful to my mother, Rena, for convincing me that I was capable of achieving any goal I set and for instilling in me a wellspring of self-confidence which sustains me to this day.I am also thankful to my brothers for their guidance, advice, and mentorship as well as for the often contrasting examples they set for me. I am grateful to Yoseif for convincing me that computers are fun, for showing me how to use them, and for introducing me to the art of computer programming by teaching me BASIC when I was seven years old. I am grateful to Daniel for setting an example of stratospheric success, for treating me like a friend rather than a little brother, and for offering a bottomless well of empathy for all the trials of graduate school and life in general. In reinforcement learning, an autonomous agent seeks an effective control policy for tackling a sequential decision task. Unlike in supervised learning, the agent never sees examples of correct or incorrect behavior but receives only a reward signal as feedback. One limitation of current methods is that they typically require a human to manually design a representation for the solution (e.g. the internal structure of a neural network). Since poor design choices can lead to grossly suboptimal policies, agents that automatically adapt their own representations have the potential to dramatically improve performance. This thesis introduces two novel approaches for automatically discovering high-performing representations.The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for vi a broad class of optimization problems. This synthesis is accomplished via 1) on-line evolutionary computation, which customizes evolutionary methods to the on-line nature of most reinforcement learning problems, and 2) evolutionary function approximation, which evolves representations for the value function approximators that are critical to the temporal difference approach.The second approach, called adaptive tile coding, automatically learns representations based on tile codings, which form piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements.This thesis also introduces a novel method for devising input representations. In particular, it presents a way to find a minimal set of features sufficient to describe the agent's current state, a challenge known as the feature selection problem. The technique, called Feature ...

show abstract

“…A recent paper by the authors (UPEC 96, Crete, Greece [11]), which included a brief review of relevant AI methods [1][2][3][4][5][6][7][8][9][10], described a feasibility study using an early warning fault detection method. This earlier paper [11] provided a case study which demonstrated that encouraging results were obtained using this approach to investigate a simulated medium length transmission line.…”

Section: Case Studiesmentioning

confidence: 99%

“…A brief description of what and how neural networks are being employed is given below. For more information relating to ANNs, see [3][4][5][6].…”

Section: /3mentioning

confidence: 99%

Update of an early warning fault detection method using artificial intelligence techniques

Wong

Ryan

Tindle

1997

IEE Half Day Colloquium on Operational Monitoring of Distribution and Transmission Systems

View full text Add to dashboard Cite

This presentation describes a research investigation to access the feasibility of using an Artificial Intelligence (AI) method to predict and detect faults at an early stage in power systems. An AI based detector has been developed to monitor and predict faults at an early stage on particular sections of power systems. The detector for this early warning fault detection device only requires external measurements taken from the input and output nodes of the power system. The AI detection system is capable of rapidly predicting a malfunction within the system. Artificial Neural Networks (ANNs) are being used as the core of the fault detector. In an earlier paper [11], a computer simulated medium length transmission line has been tested by the detector and the results clearly demonstrate the capability of the detector. Today's presentation considers a case study illustrating the suitability of this AI Technique when applied to a distribution transformer. Furthermore, an evolutionary optimisation strategy to train ANNs is also briefly discussed in this presentation, together with a 'crystal ball' view of future developments in the operation and monitoring of transmission systems in the next millennium.

show abstract

Designing application-specific neural networks using the structured genetic algorithm

Cited by 95 publications

References 7 publications

Metaheuristic design of feedforward neural networks: A review of two decades of research

Metaheuristic design of feedforward neural networks: A review of two decades of research

Adaptive Representations for Reinforcement Learning

Update of an early warning fault detection method using artificial intelligence techniques

Contact Info

Product

Resources

About